Learning to Simplify with Data Hopelessly Out of Alignment
Not on the map. Why?
Abstract (arXiv)
We consider whether it is possible to do text simplification without relying on a "parallel" corpus, one that is made up of sentence-by-sentence alignments of complex and ground truth simple sentences. To this end, we introduce a number of concepts, some new and some not, including what we call Conjoined Twin Networks, Flip-Flop Auto-Encoders (FFA) and Adversarial Networks (GAN). A comparison is made between Jensen-Shannon (JS-GAN) and Wasserstein GAN, to see how they impact performance, with stronger results for the former. An experiment we conducted with a large dataset derived from Wikipedia found the solid superiority of Twin Networks equipped with FFA and JS-GAN, over the current best performing system. Furthermore, we discuss where we stand in a relation to fully supervised methods in the past literature, and highlight with examples qualitative differences that exist among simplified sentences generated by supervision-free systems.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 15 references that are in the map. First posted on arXiv 2 Apr 2022.
Builds on
8 of 15 references.
References · 8
- 2017Improved Training of Wasserstein GANscited by 2,235
- 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
- 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
- 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 273
- 2017Are GANs Created Equal? A Large-Scale Studycited by 267
- 2017Unsupervised Neural Machine Translationcited by 149
- 2017Sentence Simplification with Deep Reinforcement Learningcited by 109
- 2018Unsupervised Neural Text Simplificationcited by 29
Built on by
Not cited yet.